Detection of blood vessels in retinal images for diagnosis of diabetics

Abstract

Early detection of blood-vessels in an retinal image and determining diameter of vessels is important for analysis and dealing of different diseases including glaucoma, hypertension and diabetic retinopathy (DR). To detect the blood-vessels in a retinal fundus images, we proposed a method consisting of four main steps. The first step is pre-processing. Initially, the contrasts of the blood vessels are not clear in the original retinal images. To improve the appearance of blood vessels we are using several image enhancement techniques. In the second step we are using various filters to improve the blood-vessels appearance in the retinal images. The third step is, feature extraction where we are extracting Grey Level Co-occurrence Matrix (GLCM) and Discrete Wavelet transform (DWT) features formed a feature vector. Finally we are applying Support Vector Machine (SVM) classifier which classifies the diseases based on the features. With the two publically available databases DRIVE and CHASE_DB1 databases we are comparing and analyzing the performance of proposed method which measures the specificity, sensitivity and accuracy.